Coder Social home page Coder Social logo

rossumai / docile Goto Github PK

View Code? Open in Web Editor NEW
106.0 13.0 7.0 606 KB

DocILE: Document Information Localization and Extraction Benchmark

Home Page: https://docile.rossum.ai

License: MIT License

Python 90.87% Shell 3.69% Dockerfile 0.08% Jupyter Notebook 5.36%
benchmark document extraction information key kie kile understanding

docile's People

Contributors

mskl avatar simsa-st avatar yash0307 avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

biswassanket huyhoang17 sia-knows huycq1712 warra07 yuni1314 buthaya

docile's Issues

suggestion: use pypdfium2 for pdf rendering

pypdfium2 does not need an additional system package, is generally faster than poppler, and used by one of your dependencies already for this very purpose (doctr).

Disclaimer: I'm the author of pypdfium2 and found this repository through GH dependents network since pypdfium2 is listed in your poetry.lock file.

Issue with repo installation 

docker-compose build jupyter[-gpu]
ERROR: The Compose file './docker-compose.yml' is invalid because:
Unsupported config option for services.jupyter: 'deploy'

The docker option does not work. We also tried to pip install the .whl build but we couldn´t find the file. Could you please take a look

Thanks in advance.

Issue when loading annotation in dataset browser 

from docile.dataset import load_predictions

KILE_PREDICTION_PATH=Path("../../data/docile/annotations/009bdcdec5c04cd3b2e31555.json")
kile_predictions = load_predictions(KILE_PREDICTION_PATH)

File c:\Users\erp\AppData\Local\Programs\Python\Python311\Lib\site-packages\docile\dataset\field.py:90, in (.0)
...
---> 37 dct_copy = dict(dct)
38 bbox = BBox(*(dct_copy.pop("bbox")))
40 # do not fail on extra keys (if participants save extra information), only warn.

ValueError: dictionary update sequence element #0 has length 1; 2 is required

Dataset License?

On the website, it states that the dataset is for research purposes. Does this mean commercial applications are blocked from using the dataset? Or what is the specific licensing?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.